// SCAN REPORT

MCP-Claude Code Bridge

5 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 4 Jul 2026

3 can modify or destroy data

2 read-only

5 tools total

Community server · catalogue entry verified 04/07/2026

How to control MCP-Claude Code Bridge ↓

TOOL MAP

What MCP-Claude Code Bridge exposes to your agents

Read (2) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous MCP-Claude Code Bridge tools

Execute · High claude_code_task This tool executes arbitrary coding tasks via Claude Code CLI. Execute · Critical run_command Shell command execution is inherently an Execute-category risk because the outcome depends entirely on the argument (the command string). Write · Medium create_project This tool creates a new directory/project structure on the filesystem.

3 of MCP-Claude Code Bridge's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP-Claude Code Bridge

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Claude Code Bridge, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "create_project": {
    "limits": [
      {
        "counter": "create_project_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "list_files": {
    "limits": [
      {
        "counter": "list_files_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register MCP-Claude Code Bridge — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP-CLAUDE CODE BRIDGE →

Instant setup, no code required.

FULL CATALOGUE

All 5 MCP-Claude Code Bridge tools

EXECUTE 2 tools

Execute claude_code_task Execute a coding task using Claude Code CLI Execute run_command Run a shell command in the project directory

WRITE 1 tools

Write create_project Create a new project directory

READ 2 tools

Read list_files List files in a project directory Read read_file Read contents of a file

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about MCP-Claude Code Bridge

How do I prevent bulk modifications through MCP-Claude Code Bridge? +

The MCP-Claude Code Bridge server has 1 write tools including create_project. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach MCP-Claude Code Bridge.

How many tools does the MCP-Claude Code Bridge MCP server expose? +

5 tools across 3 categories: Execute, Read, Write. 2 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on MCP-Claude Code Bridge? +

Register the MCP-Claude Code Bridge MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MCP-Claude Code Bridge tool call.

Deterministic rules across all 5 MCP-Claude Code Bridge tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP-CLAUDE CODE BRIDGE →

Instant setup, no code required.

5 MCP-Claude Code Bridge tools catalogued and risk-classified — across an index of 43,000+ MCP servers.